Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5262 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.9086. Min Act: -0.1700
Data Index: 8671796 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.6586. Min Act: -0.1700
Data Index: 26404 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.5649. Min Act: -0.1700
Data Index: 528629 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.5024. Min Act: -0.1700
Data Index: 1778821 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.5336. Min Act: -0.1700
Data Index: 3624167 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.4399. Min Act: -0.1700
Data Index: 1724288 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.3774. Min Act: -0.1700
Data Index: 6325297 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.4086. Min Act: -0.1700
Data Index: 2778918 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.3774. Min Act: -0.1700
Data Index: 8355314 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.3461. Min Act: -0.1700
Data Index: 1994037 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.3149. Min Act: -0.1700
Data Index: 8661362 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.3149. Min Act: -0.1700
Data Index: 1809329 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.3149. Min Act: -0.1700
Data Index: 8054087 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.3149. Min Act: -0.1700
Data Index: 8331111 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.2836. Min Act: -0.1700
Data Index: 1162365 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.2836. Min Act: -0.1700
Data Index: 6998886 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.2836. Min Act: -0.1700
Data Index: 3578438 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.2211. Min Act: -0.1700
Data Index: 8443831 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.2211. Min Act: -0.1700
Data Index: 3192266 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9086. Min Range: -7.9086
Max Act: 7.2211. Min Act: -0.1700
Data Index: 3812234 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19